Leveraging Collaborative-Filtering for Personalized Behavior Modeling

Abstract

The prevalence of mobile phones and wearable devices enables the passive capturing and modeling of human behavior at an unprecedented resolution and scale. Past research has demonstrated the capability of mobile sensing to model aspects of physical health, mental health, education, and work performance, etc. However, most of the algorithms and models proposed in previous work follow a one-size-fits-all (i.e., population modeling) approach that looks for common behaviors amongst all users, disregarding the fact that individuals can behave very differently, resulting in reduced model performance. Further, black-box models are often used that do not allow for interpretability and human behavior understanding. We present a new method to address the problems of personalized behavior classification and interpretability, and apply it to depression detection among college students. Inspired by the idea of collaborative-filtering, our method is a type of memory-based learning algorithm. It leverages the relevance of mobile-sensed behavior features among individuals to calculate personalized relevance weights, which are used to impute missing data and select features according to a specific modeling goal (e.g., whether the student has depressive symptoms) in different time epochs, i.e., times of the day and days of the week. It then compiles features from epochs using majority voting to obtain the final prediction. We apply our algorithm on a depression detection dataset collected from first-year college students with low data-missing rates and show that our method outperforms the state-of-the-art machine learning model by 5.1% in accuracy and 5.5% in F1 score. We further verify the pipeline-level generalizability of our approach by achieving similar results on a second dataset, with an average improvement of 3.4% across performance metrics. Beyond achieving better classification performance, our novel approach is further able to generate personalized interpretations of the models for each individual. These interpretations are supported by existing depression-related literature and can potentially inspire automated and personalized depression intervention design in the future.

Predicting Depression in Adolescents Using Mobile and Wearable Sensors: Multimodal Machine Learning–Based Exploratory Study

“…The PHQ-9 is an evaluative questionnaire used to assess depression severity. The PHQ-9 has been used effectively in multiple studies related to depression [ 38 , 39 ]. The questionnaire consists of a set of 9 questions with scores between 0 and 3.…”

“…Mobile sensing-based mental health studies have been conducted in the areas of bipolar disorder [27], schizophrenia [28], anxiety [29,30], stress [31,32], and depression [33][34][35][36][37][38][39]. These studies have shown that mobile sensing can play an integral role in detecting and predicting mental health-related problems.…”

“…In particular, we looked at studies that explored adolescent depression to some degree. Most previous studies were conducted with varied age groups where the adolescent population was either not a part or a very small part of the study [33][34][35][36][37][38]. However, these studies cannot be considered representative of the adolescent age category.…”

“…The work in the latter study is closely related to our endeavor and serves as an inspiration. Collaborative filtering-based study is yet another approach that has shown promise in using personalized models to derive better predictions [ 38 ]. Our study also proposes 2 personalized strategies to model individual participants using ML.…”

Predicting Multiple Sclerosis Outcomes During the COVID-19 Stay-at-home Period: Observational Study Using Passively Sensed Behaviors and Digital Phenotyping

“…We computed features from the 6 sensors of calls, heart rate, location, screen, sleep, and steps, given their potential to inform depressive symptoms [29,[44][45][46][47][48], as well as fatigue [49], MS symptom burden such as decreased mobility [27], and sleep quality [50,51].…”